© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 1943
    Prev
    Next
    INDEX
    Explanations

    measurements or quantities expressed in milligrams

    oai_token-act-pair · gpt-3.5-turbo

    measurements and quantities related to milligrams and microns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lax
    -0.74
     backstage
    -0.73
     Sovere
    -0.71
     inaction
    -0.71
     kindly
    -0.63
     frivol
    -0.61
     spont
    -0.60
    Discussion
    -0.60
     envy
    -0.59
     Claus
    -0.59
    POSITIVE LOGITS
    abytes
    1.34
    abyte
    1.29
    illion
    1.24
    awatts
    1.19
    rams
    1.14
    pees
    1.14
    ousand
    1.11
    imet
    1.04
    seconds
    0.93
    aton
    0.93
    Activations Density 0.089%

    No Known Activations